Skip to content
llmwaves

MiniMax M2

MiniMax · released Oct 23, 2025

Open weightsReasoningTool useStructured output

MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...

Specification

Context window
205K
Max output
131K
Knowledge cutoff
Not stated
Parameters
228.7B
Licence
other
Serving providers
3
Moderated
No

Intelligence

28.9

72th percentile

Coding

Coding Index

Agentic

Agentic Index

Output speed

119 t/s

Median across providers

Latency

1.17s

Time to first token

Cost per task

$0.09

Estimated

Benchmarks

Where the score comes from

The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.

Evaluation scores

Percentage correct · higher is better

  • τ²-bench (Telecom)
    86.8%
  • LiveCodeBench
    82.6%
  • MMLU-Pro
    82.0%
  • AIME 2025
    78.3%
  • GPQA Diamond
    77.7%
  • IFBench
    72.3%
  • AA-LCR (long context)
    65.0%
  • SciCode
    36.1%
  • Terminal-Bench Hard
    25.8%
  • Humanity's Last Exam
    13.7%

An evaluation missing from this list was not run for this model — it is not a zero.

View as table
EvaluationScore
τ²-bench (Telecom)86.8%
LiveCodeBench82.6%
MMLU-Pro82.0%
AIME 202578.3%
GPQA Diamond77.7%
IFBench72.3%
AA-LCR (long context)65.0%
SciCode36.1%
Terminal-Bench Hard25.8%
Humanity's Last Exam13.7%

Against its peers

Intelligence Index · this model highlighted, nearest peers in grey

Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.

View as table
ModelIntelligence
Ring-2.6-1T31.1
o331.1
Step 3.7 Flash30.9
Mistral Medium 3.530.4
Qwen3.5-35B-A3B29.9
Claude Sonnet 4.529.9
MiniMax M228.9
Claude Opus 4.128.8

Percentile among all indexed models

Intelligence72th
Mathematics73th
Terminal work67th

Pricing

What it costs to run

List prices per million tokens, plus what one representative task works out to.

List price

Input / 1M tokens
$0.255
Output / 1M tokens
$1.02
Cached input / 1M
Not offered
Blended 3:1
$0.446

One task, estimated

$0.09

Input tokens
50,000
Output tokens
80,000
Profile
Reasoning

Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).

Serving providers

Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.